Adaptive modeling of maritime autonomous surface ships with uncertainty using a weighted LS-SVR robust to outliers. (15th March 2020)

• Record Type: Journal Article
• Authors: Zhu, Man; Sun, Wuqiang; Hahn, Axel; Wen, Yuanqiao; Xiao, Changshi; Tao, Wei
• Is Part Of: Ocean engineering. Volume 200(2020)
• Publication Date: 2020-03-15
• Subjects: Maritime Autonomous Surface Ships -- Ship dynamic model -- Parameter estimation -- Uncertainty -- Optimal weighted LS-SVR; Ocean engineering -- Periodicals; Ocean engineering; Periodicals; 620.4162
• DOI: 10.1016/j.oceaneng.2020.107053
• Languages: English
• ISSNs: 0029-8018

Abstract

Abstract: Maritime Autonomous Surface Ships (MASS) have become increasingly interesting for the commercial maritime sectors as an alternative to conventional ships. For the purpose of development of MASS operations such as motion control (e.g. collision avoidance, trajectory tracking), the ship dynamic model is of significant importance for technique tests, i.e. verification and validation. The ship dynamic model should be suitable for cases which means the sufficient balance between the complexity and the accuracy of the model. This contribution is aiming to develop a robust ship dynamics modeling approach by making efforts on determining a common ship dynamic model and designing a robust identification method. A response model, i.e. the first-order nonlinear Nomoto model widely-used in ship autopilot design is selected. A robust optimal identification method named optimal DW-LSSVR is proposed by taking advantages of least square support vector regression algorithm (LS-SVR), robust 3 α principle (D), adaptive weight technique (W), and artificial bee colony algorithm (ABC for optimization). The robust 3 α principle has the function of outlier detection. Adaptive weight technique can adaptively weight support vectors to improve the sparsity of LS-SVR. Furthermore, ABC is served as the structural parameters optimizer for LS-SVR. The ships studied in this work are considered as more realistic objects with uncertain parameters induced by unmodeled terms, variation of the loading condition as well as environmental disturbances, and measurement noises. In identifying the widely-used response model for ships, the optimal DW-LSSVR method is verified and validated on both experimental measurements and simulated data. In simulation tests, the effectiveness of the proposed method in identifying the response model has been demonstrated with the use of simulated data including ones with uncertainties which are generated by activating a response model with predefined parameter values by means of step inputs in Monte Carlo simulations. Besides the simulation tests, the experimental investigation on a real Unmanned Surface Vessel (USV) using experimental zigzag maneuvers also indicates the consistency of the proposed approach. Highlights: An optimal weighted LSSVR method of MASS dynamic models was developed. The proposed method has several merits such as outlier detection, adaptive weight. Monte Carlo simulations with parameter uncertainties verify the modeling approach. A real USV demonstrated the robustness of the proposed modeling approach.